CN111400850B - Equipment fault analysis method, device, equipment and storage medium - Google Patents
Equipment fault analysis method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN111400850B CN111400850B CN201811629343.9A CN201811629343A CN111400850B CN 111400850 B CN111400850 B CN 111400850B CN 201811629343 A CN201811629343 A CN 201811629343A CN 111400850 B CN111400850 B CN 111400850B
- Authority
- CN
- China
- Prior art keywords
- data
- fault
- equipment
- determining
- residual
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 80
- 238000003860 storage Methods 0.000 title abstract description 17
- 238000004519 manufacturing process Methods 0.000 claims abstract description 81
- 238000000034 method Methods 0.000 claims abstract description 64
- 238000004088 simulation Methods 0.000 claims abstract description 50
- 238000001514 detection method Methods 0.000 claims description 97
- 238000012544 monitoring process Methods 0.000 claims description 34
- 238000012545 processing Methods 0.000 claims description 33
- 230000006870 function Effects 0.000 claims description 27
- 230000015654 memory Effects 0.000 claims description 20
- 239000000463 material Substances 0.000 claims description 10
- 238000007499 fusion processing Methods 0.000 claims description 8
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 7
- 230000005856 abnormality Effects 0.000 abstract description 11
- 238000011156 evaluation Methods 0.000 abstract description 8
- 230000008569 process Effects 0.000 description 17
- 230000002159 abnormal effect Effects 0.000 description 16
- 238000010586 diagram Methods 0.000 description 15
- 238000009826 distribution Methods 0.000 description 13
- 230000008859 change Effects 0.000 description 6
- 238000004590 computer program Methods 0.000 description 5
- 238000003745 diagnosis Methods 0.000 description 5
- 238000013178 mathematical model Methods 0.000 description 5
- 238000000926 separation method Methods 0.000 description 5
- 230000009471 action Effects 0.000 description 4
- 238000004140 cleaning Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 238000010276 construction Methods 0.000 description 4
- 230000007613 environmental effect Effects 0.000 description 4
- 238000012423 maintenance Methods 0.000 description 4
- 238000013507 mapping Methods 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 239000013598 vector Substances 0.000 description 3
- 230000032683 aging Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 238000007500 overflow downdraw method Methods 0.000 description 2
- 238000000513 principal component analysis Methods 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000009960 carding Methods 0.000 description 1
- 230000001364 causal effect Effects 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The embodiment of the application provides an equipment fault analysis method, device, equipment and storage medium, so that main reasons of equipment faults can be analyzed. The method comprises the following steps: collecting production data of a device, wherein the production data comprises: input data and output data; determining simulation output data of the equipment according to the input data, and determining corresponding residual error data according to the output data and the simulation output data; after the equipment is determined to have faults according to the residual data, factor contribution analysis is carried out according to the input data, and corresponding fault parameters are determined. Residual evaluation can be performed so as to measure the abnormality degree of the equipment and analyze the main cause of the equipment failure.
Description
Technical Field
The present disclosure relates to the field of computer technologies, and in particular, to a device failure analysis method and apparatus, an electronic device, and a storage medium.
Background
During the production and operation of industrial equipment, the industrial equipment is affected by external environment (materials, etc.), internal working conditions (equipment load, control method change, etc.), natural aging, etc., and the equipment can gradually or suddenly generate defects and fault events. The early warning of the equipment faults has important significance in realizing early fault prediction of the equipment, improving the utilization rate of the equipment, prolonging the life cycle of the equipment, preparing maintenance parts and reducing the operation and maintenance cost.
In industrial big data application, the fault diagnosis method based on equipment state simulation can solve a large number of equipment abnormality diagnosis problems, and the basic idea of the method theory is as follows: based on the theory that the measurement points show weak modes deviating from the distribution main body within a period of time after the equipment is assumed to have defects and fault states, when a large deviation exists between the theoretical health value and the actual value of the equipment, the equipment can be in an abnormal state. The deviation between the expected value and the actual value of the equipment generated in the method is the residual error.
Residual errors can be obtained through the method, but a residual error evaluation method is lacking, so that the degree of abnormality of equipment cannot be measured, and the main cause of equipment failure cannot be analyzed.
Disclosure of Invention
The embodiment of the application provides an equipment fault analysis method which is used for analyzing main reasons of equipment faults.
Correspondingly, the embodiment of the application also provides a device fault analysis device, electronic equipment and a storage medium, which are used for guaranteeing the implementation and application of the method.
In order to solve the above problems, an embodiment of the present application discloses an apparatus fault analysis method, which includes: collecting production data of a device, wherein the production data comprises: input data and output data; determining simulation output data of the equipment according to the input data, and determining corresponding residual error data according to the output data and the simulation output data; after the equipment is determined to have faults according to the residual data, factor contribution analysis is carried out according to the input data, and corresponding fault parameters are determined.
Optionally, the collecting production data of the device includes: and acquiring production data corresponding to the monitoring points through sensors of the monitoring points on the equipment.
Optionally, after the collecting the production data of the device, the method further includes: sorting the production data according to a time sequence; and processing the sorted production data according to the set window to respectively obtain corresponding input characteristic data and output characteristic data.
Optionally, the determining the simulated output data of the device according to the input data, and determining the corresponding residual data according to the output data and the simulated output data includes: inputting the input characteristic data into a simulator to obtain simulation output data corresponding to the equipment, wherein the simulator is trained according to historical production data; and determining a corresponding residual sequence according to the output characteristic data and the simulation output data.
Optionally, the method further comprises: performing fault analysis on the residual sequence to determine a corresponding fault detection value; if the fault detection value exceeds a fault threshold, the equipment has a fault; if the fault detection value does not exceed the fault threshold, the equipment has no fault.
Optionally, the performing fault analysis on the residual sequence to determine a corresponding fault detection value includes: determining a fault detection function of a corresponding type according to the type of the residual sequence, wherein the type comprises: univariate classes and/or multivariate classes; and determining a fault detection value corresponding to the residual sequence according to the fault detection function of the corresponding type, wherein the fault threshold is related to the false alarm rate.
Optionally, factor contribution analysis is performed according to the input data, and determining the corresponding fault parameter includes: fusion processing is carried out on a plurality of input data according to a set rule, so that a plurality of fault influence factors are obtained; performing factor contribution analysis on the plurality of fault influence factors to obtain a fault influence factor with the largest contribution rate; and determining at least one input data corresponding to the fault influence factor with the largest contribution rate as a corresponding fault parameter.
Optionally, performing factor contribution analysis on the plurality of fault impact factors to obtain a fault impact factor with the largest contribution rate, including: calculating fault detection statistics through a preset fault analyzer and a fault influence factor; calculating contribution rates of the plurality of fault influence factors to the fault detection statistics respectively; and determining a fault influence factor with the largest contribution rate.
The embodiment of the application also discloses a device for analyzing equipment faults, which comprises: the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring production data of equipment, and the production data comprises: input data and output data; the residual error determining module is used for determining simulation output data of the equipment according to the input data and determining corresponding residual error data according to the output data and the simulation output data; and the fault analysis module is used for carrying out factor contribution analysis according to the input data after determining that the equipment has faults according to the residual data, and determining corresponding fault parameters.
Optionally, the collection module is configured to collect production data corresponding to the monitoring points through a sensor of the monitoring points on the device.
Optionally, the apparatus further includes: the data processing module is used for sorting the production data according to the time sequence; and processing the sorted production data according to the set window to respectively obtain corresponding input characteristic data and output characteristic data.
Optionally, the residual determination module includes: the simulation processing sub-module is used for inputting the input characteristic data into a simulator to obtain simulation output data corresponding to the equipment, wherein the simulator is trained according to historical production data; and the residual sequence determining submodule is used for determining a corresponding residual sequence according to the output characteristic data and the simulation output data.
Optionally, the apparatus further includes: the fault detection module is used for carrying out fault analysis on the residual sequence and determining a corresponding fault detection value; if the fault detection value exceeds a fault threshold, the equipment has a fault; if the fault detection value does not exceed the fault threshold, the equipment has no fault.
Optionally, the fault detection module includes: a function determining submodule, configured to determine a fault detection function of a corresponding type according to a type of the residual sequence, where the type includes: univariate classes and/or multivariate classes; and the detection value determining submodule is used for determining a fault detection value corresponding to the residual sequence according to the fault detection function of the corresponding type, and the fault threshold is related to the false alarm rate.
Optionally, the fault analysis module includes: the factor determination submodule is used for carrying out fusion processing on a plurality of input data according to a set rule to obtain a plurality of fault influence factors; the contribution rate analysis submodule is used for carrying out factor contribution analysis on the plurality of fault influence factors to obtain the fault influence factor with the largest contribution rate; and the parameter determination submodule is used for determining at least one input data corresponding to the fault influence factor with the largest contribution rate as a corresponding fault parameter.
Optionally, the contribution rate analysis sub-module is used for calculating fault detection statistics through a preset fault analyzer and a fault influence factor; calculating contribution rates of the plurality of fault influence factors to the fault detection statistics respectively; and determining a fault influence factor with the largest contribution rate.
The embodiment of the application also discloses electronic equipment, which comprises: a processor; and a memory having executable code stored thereon that, when executed, causes the processor to perform the device fault analysis method as described in one or more of the embodiments of the present application.
One or more machine-readable media having stored thereon executable code that, when executed, causes a processor to perform an apparatus fault analysis method as described in one or more of the embodiments of the present application are also disclosed.
Compared with the prior art, the embodiment of the application has the following advantages:
in this embodiment of the present application, production data of a device may be collected, where the production data includes input data and output data, then, according to the input data, simulation output data of the device is determined, and corresponding residual error data is determined according to the output data and the simulation output data, so as to perform residual error evaluation, measure an abnormal degree of the device, and after determining that the device has a fault according to the residual error data, perform factor contribution analysis according to the input data, determine corresponding fault parameters, and can analyze a main cause of the fault of the device.
Drawings
FIG. 1 is a flow chart of steps of an embodiment of an apparatus failure analysis method of the present application;
FIG. 2 is a schematic diagram of an example of an input-output mapping of an embodiment of the present application;
FIGS. 3A, 3B, and 3C are several residual distribution diagrams of embodiments of the present application;
FIG. 4 is a schematic diagram of an example of a module for device failure analysis according to an embodiment of the present application;
FIG. 5 is a flow chart of steps of another embodiment of an apparatus failure analysis method of the present application;
FIG. 6 is a block diagram of an embodiment of an apparatus for device fault analysis of the present application;
FIG. 7 is a block diagram of another embodiment of an apparatus for device fault analysis of the present application;
fig. 8 is a schematic structural diagram of an apparatus according to an embodiment of the present application.
Detailed Description
In order that the above-recited objects, features and advantages of the present application will become more readily apparent, a more particular description of the invention briefly described above will be rendered by reference to specific embodiments that are illustrated in the appended drawings.
During the production and operation of industrial equipment, the industrial equipment is affected by external environment (materials, etc.), internal working conditions (equipment load, control method change, etc.), natural aging, etc., and the equipment can gradually or suddenly generate defects and fault events. The early warning of the equipment faults has important significance in realizing early fault prediction of the equipment, improving the utilization rate of the equipment, prolonging the life cycle of the equipment, preparing maintenance parts and reducing the operation and maintenance cost.
The method for evaluating the residual error comprises the steps of collecting production data of equipment, including input data and output data, determining simulation output data of the equipment according to the input data, determining corresponding residual error data according to the output data and the simulation output data, and evaluating the residual error to measure the abnormality degree of the equipment, wherein a residual error evaluation method can be determined according to the residual error data and historical fault records of the equipment, a fault threshold is determined, factor contribution analysis can be performed according to the input data after the equipment is determined to have faults according to the fault threshold, so that corresponding fault parameters are determined, and the main cause of the faults of the equipment can be analyzed.
Referring to fig. 1, a flow chart of steps of an embodiment of an equipment failure analysis method of the present application is shown.
Step 102, collecting production data of the equipment.
Production data of the equipment can be collected in the running process of the equipment, the production data refers to various data input and output in the generating running process, and the production data comprises: input data and output data, wherein the input data refer to data of an input device, such as materials, energy sources and the like put into the device, the output data refer to data output by the device, such as products output by the device and the like, and the input data and the output data are different according to different types of the device. For example, if the device is a boiler, the input data may include water volume, air volume, material, induced draft, etc., and the output data is steam volume. The position corresponding to various production data of the equipment can be used as a monitoring point, and the sensor is arranged at the detection point, so that the production data corresponding to the monitoring point can be collected through the sensor on the monitoring point in the equipment, and the sensor can also be determined according to the type of the production data, such as measuring water quantity, wind power, the volume and the quality of materials, and measuring steam flow. Wherein the sensor may be a single sensor or a combination of sensors. In one embodiment, the monitoring points include environmental monitoring points, control monitoring points and output monitoring points, the input data in the corresponding production data include environmental variable data, equipment control variable data, the environmental variable data include temperature data, humidity data and the like, and the equipment control variable data includes air supply quantity data, water quantity data, material data and the like by taking a boiler as an example.
Step 104, determining simulation output data of the equipment according to the input data, and determining corresponding residual data according to the output data and the simulation output data.
When the output data (such as capacity) of the device deviates from the input data (such as input amount), that is, the expected mapping relationship between the input data and the output data is destroyed, the device may be in an abnormal state, so that the device in the normal operation state may be subjected to simulation processing, and the simulation output data of the device in the output data corresponding to the normal operation state is obtained, residual data may be obtained according to the simulation output data and the collected device output data, and the parameter data may be a difference value between the simulation output data (such as an estimated value in the normal operation state of the device) and the output data (such as an actual output value of the device), so as to determine whether the device has a fault. The simulation output data are obtained by training a large amount of historical production data of equipment, and when the equipment is in a normal healthy movement process, residual errors are supposed to fluctuate within a small range above and below a healthy value and random noise information is contained.
In an alternative embodiment, the determining the simulated output data of the device according to the input data, and determining the corresponding residual data according to the output data and the simulated output data includes: inputting the input characteristic data into a simulator to obtain simulation output data corresponding to the equipment, wherein the simulator is trained according to historical production data; and determining a corresponding residual sequence according to the output characteristic data and the simulation output data.
In an alternative embodiment of the present application, production data such as input data and output data of the device in a normal state may be collected in advance, a data model may be constructed, and model training may be performed based on the production data to obtain a simulator, where the simulator may simulate a mapping relationship between the input data and the output data, so as to simulate the output data of the device in the normal state based on the input data. The simulator can be also called a simulation model, a data set for simulating equipment production, and the like, and can be trained based on sound field data and a mathematical model in a normal state of the equipment, so that output data in the normal state of the equipment can be simulated based on an input database. The mathematical model is a scientific or engineering model constructed by using a mathematical logic method and a mathematical language, and is a mathematical structure which is expressed in a generalized or approximate way by adopting the mathematical language aiming at referring to the characteristic or the quantity dependency relationship of a certain object system, and the mathematical structure is a pure relationship structure of a certain system which is characterized by means of mathematical symbols. The mathematical model may be one or a set of algebraic, differential, integral or statistical equations and combinations thereof by which the interrelationship or causal relationship between the variables of the system is described quantitatively or qualitatively. In addition to mathematical models described by equations, there are models described by other mathematical tools, such as algebra, geometry, topology, mathematical logic, etc. Wherein the mathematical model describes the behavior and characteristics of the system rather than the actual structure of the system. The simulator performs model training by adopting a machine learning method, a deep learning method and the like, wherein the machine learning method can comprise linear regression, a decision tree, a random forest, xgboost, lightgbm and the like, and the deep learning method can comprise a convolutional neural network (Convolutional Neural Networks, CNN), a Long Short-Term Memory (LSTM), a gating cycle unit (Gated Recurrent Unit, GRU) and the like.
As shown in fig. 2, taking the boiler field as an example, the input data includes: water quantity, air quantity, materials, induced air and the like, and output data comprise steam quantity. The production data collected by the boiler in a normal working state is constructed into a memory matrix, row vectors of the matrix represent the production data of all monitoring points at a certain moment, and column vectors represent the production data of the monitoring points at different moments. The measuring point relation (equipment input data and output data) between the main system and each subsystem of the carding boiler is used for constructing a simulator of the mapping relation of the input data and the output data.
After the production data such as the input data and the output data of the equipment are obtained, the input data can be input into the simulator for simulation processing, so that the simulation output data output by the simulator, namely the output data in the normal operation state of the simulation equipment, is obtained. The output characteristic data and the simulated output data may then be used to determine corresponding residual data. The device abnormality diagnosis method based on the local distribution test can simulate output data yhat aiming at actual output data y of the device, and residual error r=yhat-y.
In an alternative embodiment, after the collecting the production data of the device, the method further includes: sorting the production data according to a time sequence; and processing the sorted production data according to the set window to respectively obtain corresponding input characteristic data and output characteristic data. After the production data of the device is collected, the production data may be further preprocessed, where the preprocessing operation includes: a time-series data regularization operation, a data cleansing operation, and a feature construction operation. The time sequence data regulating operation can respectively process each type of production data into data based on time according to the updating granularity of the production data, such as environmental variable data including temperature data, humidity data and the like, equipment control variable data including air quantity data, water quantity data, material data and the like, and output data and the like of equipment according to time sequence, so as to obtain the production data regulated according to time sequence, such as a data table with a time stamp corresponding to a plurality of monitoring points. The data cleaning operation can be used for cleaning abnormal values of data, processing missing values and the like, wherein the abnormal value cleaning method comprises a 3sigma method, a quantile method and the like; the missing value processing may be processed using statistics-based padding (e.g., mean processing), post-padding, individual processing, and the like. The feature construction operation may construct a corresponding feature derivative based on the feature change frequency corresponding to the production data, wherein the feature change frequency corresponding to the production data may be determined based on statistics, and statistics corresponding to the production data may be obtained as the feature derivative. The window corresponding to the production data can be determined to obtain a corresponding set window, wherein the window widths of the input data and the output data can be the same or continuous, the window width of the set window is related to time, the window width can be set according to the time length, so that the derivative quantity corresponding to the production data is constructed through the set window, and the production characteristic data such as the mean value, the variance, the maximum value, the minimum value and the like corresponding to the production data in the set time length such as 1 and 2 comprise the input characteristic data, the output characteristic data and the like. In this embodiment of the present application, the selection of the window width of the set window may be determined from the service according to how long the characteristic output of the device will react to the working condition, for example, in the boiler industry, considering that the change of the steam quantity mostly reacts based on the working condition within 30 minutes, and 30 minutes may be selected as the window width.
And step 106, judging whether the equipment has faults or not according to the residual data.
The fault threshold value may be determined based on whether the residual analysis device has a fault, wherein a residual evaluation method is determined from residual data and a historical fault record, so as to perform device abnormality/fault determination. In an alternative embodiment, the residual sequence may be subjected to fault analysis to determine a corresponding fault detection value; if the fault detection value exceeds a fault threshold, the equipment has a fault; if the fault detection value does not exceed the fault threshold, the equipment has no fault. Based on the distribution characteristics of the residual errors, equipment faults can be analyzed, and if the distribution of the residual errors deviates from the characteristics corresponding to the normal state, the equipment faults can be determined. The fault detection value of the equipment can be determined through analysis, a corresponding fault threshold is set, and whether the equipment has faults or not is determined based on the fault detection value and the fault threshold. If yes, confirm that the device has a fault, step 108 may be executed, if not, confirm that the device has no fault, and end the flow.
The fault detection function is constructed as q (k), q > Td represents that the equipment has faults according to a preset fault threshold Td, and q < = Td represents that the equipment has no faults. The fault threshold is related to the false alarm rate of the equipment, the false alarm rate refers to the probability of false alarm of the equipment, and the false alarm rate can control the possibility of false alarm of the equipment. The fault threshold may be adjusted based on the verification error rate and when the false alarm rate is defined as alpha, the fault-free condition should be within the range of alpha.
The performing fault analysis on the residual sequence to determine a corresponding fault detection value includes: determining a fault detection function of a corresponding type according to the type of the residual sequence, wherein the type comprises: univariate classes and/or multivariate classes; and determining a fault detection value corresponding to the residual sequence according to the fault detection function of the corresponding type, wherein the fault threshold is related to the false alarm rate. The embodiment of the application can make binary assumption on the residual sequence, and for no fault H0, E (r) =0, and for fault H1, E (r) >0 or E (r) <0, r is the residual sequence.
For the residual sequence r=yhat-y of the univariate class, in a big data scene, the residual sequence is theoretically subjected to normal distribution with the mean value of 0, namely N (0, sigma), and the sigma is the standard deviation of the residual sequence. A fault detection function q= (x_hat-0)/(s/sqrt (n)) may be constructed;
wherein x_hat is the average number of residual subsequences, s is the standard deviation of the residual subsequences, and n is the number of the residual subsequences. Setting a fault threshold Td, and if q is greater than Td, indicating that the equipment has faults, and if q < = Td, indicating that the equipment has no faults.
In the residual distribution diagram shown in fig. 3, the residual sequence shown in fig. 3A fluctuates in a small range above and below the health value, and is a normal residual sequence, and at this time, the device operates normally; the residual sequence shown in fig. 3B is increased in fluctuation, and suspected equipment is abnormal in operation; the residual sequence shown in fig. 3C is forward shifted, suspected of device operational anomalies.
For a residual sequence ri=yihat-yi of a multivariate class, assuming that there are m sensors, under a big data scene, the residual of a single sensor is theoretically subject to a normal distribution with a mean value of 0, i.e., N (0, sigma), which is the standard deviation of the residual sequence. After the corresponding conversion ri= (ri-u)/sigma, the residual sequence obeys a standard normal distribution N (0, 1). A fault detection function q= Σriri may be constructed;
the residual sequence square and the chi-square distribution with the compliance degree of freedom of m of the plurality of independent sensors are recorded as follows: χ2 (m). Setting a fault threshold Td, and if q is greater than Td, indicating that the equipment has faults, and if q < = Td, indicating that the equipment has no faults.
Therefore, the fault detection function is used for analyzing, the obtained fault detection value q can measure the abnormality degree of the equipment to a certain extent, and the equipment abnormality score is given.
And step 108, performing factor contribution analysis according to the input data to determine corresponding fault parameters.
On the basis of determining that the equipment has faults according to the residual data, the embodiment of the application can further analyze the fault reasons of the equipment. Fault analysis may be performed using a fault separation method based on factor contributions, which may be based on principal component analysis (principal components analysis, PCA) techniques, also referred to as principal component analysis techniques, to determine which key factors result in a change in the device by primarily affecting the factors from among a plurality of factor separations affecting the device. The PCA method can integrate multiple indexes into fewer comprehensive indexes, the fewer comprehensive indexes are not related to each other, most of information of the original indexes can be provided, then a fault analyzer corresponding to a required PCA model is built based on the contribution rate, and the fault analyzer can be used for carrying out standardized processing and building and training on the PCA model based on steady-state data of equipment under the specified working condition.
In an alternative embodiment, factor contribution analysis is performed according to the input data, and corresponding fault parameters are determined, including: fusion processing is carried out on a plurality of input data according to a set rule, so that a plurality of fault influence factors are obtained; performing factor contribution analysis on the plurality of fault influence factors to obtain a fault influence factor with the largest contribution rate; and determining at least one input data corresponding to the fault influence factor with the largest contribution rate as a corresponding fault parameter. The method comprises the steps of carrying out fusion processing on a plurality of input data according to a set rule to obtain a plurality of fault influence factors, wherein the input parameters required to be fused according to different set rules are different, and the input factors are set according to requirements, so that a plurality of indexes are fused into fewer comprehensive indexes to obtain a plurality of fault influence factors, then carrying out factor contribution analysis on the plurality of fault influence factors to determine the contribution rate of each fault influence factor to the whole influence, wherein the contribution rate refers to the influence of the fault influence factors on the whole data, so that the fault influence factor with the largest contribution rate is obtained, and determining at least one input data corresponding to the fault influence factor with the largest contribution rate as a corresponding fault parameter.
Performing factor contribution analysis on the plurality of fault influence factors to obtain a fault influence factor with the largest contribution rate, wherein the factor contribution analysis comprises the following steps: calculating fault detection statistics through a preset fault analyzer and a fault influence factor; calculating contribution rates of the plurality of fault influence factors to the fault detection statistics respectively; and determining a fault influence factor with the largest contribution rate.
After the preset fault analyzer is determined, fault detection statistics can be calculated based on the preset fault analyzer and a plurality of fault influence factors, namely, fault detection statistics of the whole fault influence factors are determined based on the fault analyzer, then the influence magnitude of each fault influence factor is separated based on the fault detection statistics, namely, the contribution rate of the fault influence factors to the fault detection statistics is calculated, and the fault influence factor with the largest contribution rate is obtained.
In the embodiment of the application, the Q and/or T2 statistics may be used as the fault detection statistics in the PCA technology, so that the first fault detection statistic Q and/or the second fault detection statistic T2 may be calculated by the fault analyzer and the fault influencing factor. The contribution of the fault influencing factor in the fault detection statistics Q, T is then fault separated.
For the first fault detection statistic Q, calculating the contribution rate of the fault influence factor to the fault detection statistic as follows, where the contribution rate of the jth fault influence factor xj to the statistic Q is:
ContQj＝xj_hat–xj_hat_standard
wherein xj_hat is the standardized variable xj_hat, and xj_hat_standard is the standard value of the standardized variable xj corresponding to the model.
For the second fault detection statistic T2, the contribution rate of the fault influencing factor to the fault detection statistic is calculated as follows: the following among a principal elements can be satisfied: (ti/λi) > r principal component variables of Td/α (r < =a), then 2) calculate the contribution rate of the j-th variable xj to the T2 statistic:
ConTj＝∑(ti/λi)*pij*xj_hat，i＝1,2,…r
where ti is the ith score vector of the pca model, λi is the corresponding correlation matrix eigenvalue, td is the control limit, α is the significance level, and pij is the value of the ith row and the jth column in the principal element matrix.
The calculated contribution rates of the variable xj to all the overrun principal component variables are calculated according to 0 when the value is smaller than 0, and the contribution rate of the variable xj to T2 is the sum of all the contribution rates.
Therefore, the comprehensive diagnosis of the overall abnormal condition of the equipment can be performed under the condition of multiple residual errors by a multi-factor fusion method.
Therefore, the abnormal state of the equipment is alarmed, and the method can be realized through the processes of data acquisition, data processing, simulation processing, abnormal judgment, residual analysis and the like. In one example, based on the above described equipment failure analysis process, a residual generation module and a residual evaluation module may be determined, as shown in fig. 4. The residual error generating module 402 includes stages of data acquisition, data processing, simulation processing, and the like, and the residual error evaluating module 404 includes stages of anomaly determination, residual error analysis, and the like. In the data acquisition stage, in the running process of the equipment, the data can be acquired and stored through a sensor, an equipment controller and the like, and the data can be synchronized to a cloud server in real time; the cloud server processes the data in real time, wherein the processing process comprises regular time sequence data, basic cleaning of the data and feature construction, and the feature derivative construction can be performed based on equipment mechanism, such as moving window average value and the like; the simulation processing can also be performed based on the equipment simulator, such as performing simulation output data of equipment through a machine learning method, then determining a corresponding residual sequence, and then performing equipment abnormality judgment and analysis.
After the residual error is concerned, the residual error evaluation module measures the degree of equipment abnormality through the distribution analysis of the residual error local space, for example, by constructing a fault detection function, determining a core fault variable through factor contribution, and the like, and constructing a fusion method based on the residual error space and the factor contribution analysis, thereby improving the accuracy and the agility of fault detection and fault separation.
Based on the above embodiments, the present embodiment may make a comprehensive diagnosis of the overall abnormal condition of the device based on residual analysis of the device failure and parameters affecting the device failure.
Referring to fig. 5, a flowchart of steps of another device failure analysis method embodiment of the present application is shown.
Step 502, acquiring production data of corresponding monitoring points through sensors of the monitoring points on the equipment.
Step 504, sorting the production data according to time sequence; and processing the sorted production data according to the set window to respectively obtain corresponding input characteristic data and output characteristic data.
And step 506, inputting the input characteristic data into a simulator to obtain simulation output data corresponding to the equipment.
And step 508, determining a corresponding residual sequence according to the output characteristic data and the simulation output data.
And 510, performing fault analysis on the residual sequence to determine a corresponding fault detection value. Wherein, according to the type of the residual sequence, determining a fault detection function of a corresponding type; and determining a fault detection value corresponding to the residual sequence according to the fault detection function of the corresponding type.
Step 512, determining whether the fault detection value exceeds a fault threshold. If yes, the fault detection value exceeds the fault threshold, step 516 is executed; if not, the fault detection value does not exceed the fault threshold, step 514 is performed.
In step 514, the device is not malfunctioning.
In step 516, the device is malfunctioning.
And 518, performing fusion processing on the plurality of input data according to the set rule to obtain a plurality of fault influence factors.
And step 520, performing factor contribution analysis on the plurality of fault influence factors to obtain the fault influence factor with the largest contribution rate. And performing factor contribution analysis on the plurality of fault influence factors to obtain a fault influence factor with the largest contribution rate, wherein the factor contribution analysis comprises the following steps: calculating fault detection statistics through a preset fault analyzer and a fault influence factor; calculating contribution rates of the plurality of fault influence factors to the fault detection statistics respectively; and determining a fault influence factor with the largest contribution rate.
And 522, determining at least one input data corresponding to the fault influence factor with the largest contribution rate as a corresponding fault parameter.
Therefore, the embodiment of the application can establish a complete abnormal state early warning process based on the service characteristics, the operation mechanism and the like of the equipment, such as establishing the abnormal state early warning process aiming at the equipment with input, output, heat energy conversion modes and the like.
The embodiment of the application can be used for carrying out fault discrimination on the residual errors based on the spatial distribution of a section of residual error sequences and carrying out fault discrimination by a statistical assumption method, so that the accuracy of fault detection is improved. The fault threshold for fault discrimination can be adjusted according to the false alarm rate, so that the fault detection is more flexible.
Under the condition of multiple residual errors, the method comprehensively diagnoses the overall abnormal condition of the equipment, performs fault separation through factor contribution, determines a measuring point value with larger contribution quantity, and locates fault variables.
It should be noted that, for simplicity of description, the method embodiments are shown as a series of acts, but it should be understood by those skilled in the art that the embodiments are not limited by the order of acts described, as some steps may occur in other orders or concurrently in accordance with the embodiments. Further, those skilled in the art will appreciate that the embodiments described in the specification are all preferred embodiments and that the acts referred to are not necessarily required by the embodiments of the present application.
On the basis of the above embodiment, the present embodiment further provides an apparatus fault analysis device, which is applied to electronic devices such as a terminal device and a server.
Referring to fig. 6, a block diagram illustrating an embodiment of an apparatus fault analysis device according to the present application may specifically include the following modules:
an acquisition module 602, configured to acquire production data of a device, where the production data includes: input data and output data.
The residual determining module 604 is configured to determine simulated output data of the device according to the input data, and determine corresponding residual data according to the output data and the simulated output data.
The fault analysis module 606 is configured to perform factor contribution analysis according to the input data after determining that the device has a fault according to the residual data, and determine a corresponding fault parameter.
In summary, production data of the device can be collected, the production data comprises input data and output data, then simulation output data of the device is determined according to the input data, corresponding residual error data is determined according to the output data and the simulation output data, so that residual error evaluation is performed, the degree of abnormality of the device is measured, factor contribution analysis can be performed according to the input data after the device is determined to have a fault according to the residual error data, corresponding fault parameters are determined, and the main cause of the fault of the device can be analyzed.
Referring to fig. 7, a block diagram illustrating an embodiment of an apparatus fault analysis device according to the present application may specifically include the following modules:
an acquisition module 602, configured to acquire production data of a device, where the production data includes: input data and output data.
A data processing module 608, configured to sort the production data according to a time sequence; and processing the sorted production data according to the set window to respectively obtain corresponding input characteristic data and output characteristic data.
The residual determining module 604 is configured to determine simulated output data of the device according to the input data, and determine corresponding residual data according to the output data and the simulated output data.
The fault detection module 610 is configured to perform fault analysis on the residual sequence, and determine a corresponding fault detection value; if the fault detection value exceeds a fault threshold, the equipment has a fault; if the fault detection value does not exceed the fault threshold, the equipment has no fault.
The fault analysis module 606 is configured to perform factor contribution analysis according to the input data after determining that the device has a fault according to the residual data, and determine a corresponding fault parameter.
The collection module 602 is configured to collect production data corresponding to the monitoring points through sensors of the monitoring points on the device.
The residual determination module 604 includes: a simulation processing submodule 6042 and a residual sequence determination submodule 6044, wherein:
and a simulation processing submodule 6042, configured to input the input feature data into a simulator to obtain simulation output data corresponding to the device, where the simulator is trained according to historical production data.
And a residual sequence determining submodule 6044, configured to determine a corresponding residual sequence according to the output characteristic data and the simulation output data.
The fault detection module 610 includes: function determination submodule 6102 and detection value determination submodule 6104, wherein:
a function determination submodule 6102, configured to determine a fault detection function of a corresponding type according to the type of the residual sequence, where the type includes: univariate classes and/or multivariate classes.
The detection value determining submodule 6104 is configured to determine a fault detection value corresponding to the residual sequence according to the fault detection function of the corresponding type, where the fault threshold is related to the false alarm rate.
The fault analysis module 606 includes: factor determination submodule 6062 and contribution rate analysis submodule 6064, wherein:
The factor determination submodule 6062 is configured to perform fusion processing on a plurality of input data according to a set rule, so as to obtain a plurality of fault impact factors.
The contribution rate analysis submodule 6064 is used for carrying out factor contribution analysis on the plurality of fault influence factors to obtain the fault influence factor with the largest contribution rate;
and the parameter determining submodule 6066 is used for determining at least one input data corresponding to the fault influence factor with the largest contribution rate as a corresponding fault parameter.
The contribution rate analysis submodule 6064 is used for calculating fault detection statistics through a preset fault analyzer and a fault influence factor; calculating contribution rates of the plurality of fault influence factors to the fault detection statistics respectively; and determining a fault influence factor with the largest contribution rate.
Therefore, the embodiment of the application can establish a complete abnormal state early warning process based on the service characteristics, the operation mechanism and the like of the equipment, such as establishing the abnormal state early warning process aiming at the equipment with input, output, heat energy conversion modes and the like.
The embodiment of the application can be used for carrying out fault discrimination on the residual errors based on the spatial distribution of a section of residual error sequences and carrying out fault discrimination by a statistical assumption method, so that the accuracy of fault detection is improved. The fault threshold for fault discrimination can be adjusted according to the false alarm rate, so that the fault detection is more flexible.
Under the condition of multiple residual errors, the method comprehensively diagnoses the overall abnormal condition of the equipment, performs fault separation through factor contribution, determines a measuring point value with larger contribution quantity, and locates fault variables.
The embodiment of the application also provides a non-volatile readable storage medium, where one or more modules (programs) are stored, where the one or more modules are applied to a device, and the device may be caused to execute instructions (instractions) of each method step in the embodiment of the application.
Embodiments of the present application provide one or more machine-readable media having instructions stored thereon that, when executed by one or more processors, cause an electronic device to perform a method as described in one or more of the above embodiments. In this embodiment of the present application, the electronic device includes various types of devices such as a terminal device, a server (a cluster), and the like.
Embodiments of the present disclosure may be implemented as an apparatus for performing a desired configuration using any suitable hardware, firmware, software, or any combination thereof, which may include electronic devices such as terminal devices, servers (clusters), etc. Fig. 8 schematically illustrates an example apparatus 800 that may be used to implement various embodiments described herein.
For one embodiment, fig. 8 illustrates an example apparatus 800 having one or more processors 802, a control module (chipset) 804 coupled to at least one of the processor(s) 802, a memory 806 coupled to the control module 804, a non-volatile memory (NVM)/storage 808 coupled to the control module 804, one or more input/output devices 810 coupled to the control module 804, and a network interface 812 coupled to the control module 804.
The processor 802 may include one or more single-core or multi-core processors, and the processor 802 may include any combination of general-purpose or special-purpose processors (e.g., graphics processors, application processors, baseband processors, etc.). In some embodiments, the apparatus 800 can be used as a terminal device, a server (cluster), or the like in the embodiments of the present application.
In some embodiments, the apparatus 800 can include one or more computer-readable media (e.g., memory 806 or NVM/storage 808) having instructions 814 and one or more processors 802 coupled with the one or more computer-readable media and configured to execute the instructions 814 to implement the modules to perform the actions described in this disclosure.
For one embodiment, the control module 804 may include any suitable interface controller to provide any suitable interface to at least one of the processor(s) 802 and/or any suitable device or component in communication with the control module 804.
The control module 804 may include a memory controller module to provide an interface to the memory 806. The memory controller modules may be hardware modules, software modules, and/or firmware modules.
Memory 806 may be used to load and store data and/or instructions 814 for device 800, for example. For one embodiment, memory 806 may include any suitable volatile memory, such as, for example, a suitable DRAM. In some embodiments, memory 806 may include double data rate type four synchronous dynamic random access memory (DDR 4 SDRAM).
For one embodiment, control module 804 may include one or more input/output controllers to provide an interface to NVM/storage 808 and input/output device(s) 810.
For example, NVM/storage 808 may be used to store data and/or instructions 814. NVM/storage 808 may include any suitable nonvolatile memory (e.g., flash memory) and/or may include any suitable nonvolatile storage device(s) (e.g., one or more Hard Disk Drives (HDDs), one or more Compact Disc (CD) drives, and/or one or more Digital Versatile Disc (DVD) drives).
NVM/storage 808 may include storage resources that are physically part of the device on which apparatus 800 is installed or may be accessible by the device without necessarily being part of the device. For example, NVM/storage 808 may be accessed over a network via input/output device(s) 810.
Input/output device(s) 810 may provide an interface for apparatus 800 to communicate with any other suitable devices, input/output device 810 may include communication components, audio components, sensor components, and the like. Network interface 812 may provide an interface for device 800 to communicate over one or more networks, and device 800 may communicate wirelessly with one or more components of a wireless network according to any of one or more wireless network standards and/or protocols, such as accessing a wireless network based on a communication standard, such as WiFi, 2G, 3G, 4G, 5G, etc., or a combination thereof.
For one embodiment, at least one of the processor(s) 802 may be packaged together with logic of one or more controllers (e.g., memory controller modules) of the control module 804. For one embodiment, at least one of the processor(s) 802 may be packaged together with logic of one or more controllers of the control module 804 to form a System In Package (SiP). For one embodiment, at least one of the processor(s) 802 may be integrated on the same die with logic of one or more controllers of the control module 804. For one embodiment, at least one of the processor(s) 802 may be integrated on the same die with logic of one or more controllers of the control module 804 to form a system on chip (SoC).
In various embodiments, the apparatus 800 may be, but is not limited to being: a server, a desktop computing device, or a mobile computing device (e.g., a laptop computing device, a handheld computing device, a tablet, a netbook, etc.), among other terminal devices. In various embodiments, device 800 may have more or fewer components and/or different architectures. For example, in some embodiments, the apparatus 800 includes one or more cameras, a keyboard, a Liquid Crystal Display (LCD) screen (including a touch screen display), a non-volatile memory port, multiple antennas, a graphics chip, an Application Specific Integrated Circuit (ASIC), and a speaker.
The detection device can adopt a main control chip as a processor or a control module, sensor data, position information and the like are stored in a memory or an NVM/storage device, a sensor group can be used as an input/output device, and a communication interface can comprise a network interface.
For the device embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments for relevant points.
In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described by differences from other embodiments, and identical and similar parts between the embodiments are all enough to be referred to each other.
Embodiments of the present application are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present embodiments have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the embodiments of the present application.
Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or terminal device comprising the element.
The foregoing has described in detail a method and apparatus for device fault analysis, an electronic device and a storage medium, and specific examples have been used herein to illustrate the principles and embodiments of the present application, where the foregoing examples are provided to assist in understanding the method and core ideas of the present application; meanwhile, as those skilled in the art will have modifications in the specific embodiments and application scope in accordance with the ideas of the present application, the present description should not be construed as limiting the present application in view of the above.
Claims (14)
1. A method for equipment failure analysis, said method comprising:
the method comprises the steps of collecting production data corresponding to monitoring points through sensors of the monitoring points on equipment, wherein the production data comprise: the monitoring points comprise environment monitoring points, control monitoring points and output monitoring points, and the input data comprises at least one of the following: temperature data, humidity data, air supply quantity data, water quantity data and material data;
determining simulation output data of the equipment according to the input data, and determining corresponding residual error data according to the output data and the simulation output data;
After determining that the equipment has faults according to the residual data, carrying out fusion processing on a plurality of input data according to a set rule to obtain a plurality of fault influence factors;
calculating fault detection statistics through a preset fault analyzer and a fault influence factor;
calculating contribution rates of the plurality of fault influence factors to the fault detection statistics respectively;
determining a fault influence factor with the largest contribution rate;
and determining at least one input data corresponding to the fault influence factor with the largest contribution rate as a corresponding fault parameter.
2. The method of claim 1, wherein collecting production data for the device comprises:
and acquiring production data corresponding to the monitoring points through sensors of the monitoring points on the equipment.
3. The method of claim 1, further comprising, after the collecting the production data of the device:
sorting the production data according to a time sequence;
and processing the sorted production data according to the set window to respectively obtain corresponding input characteristic data and output characteristic data.
4. A method according to claim 3, wherein said determining simulated output data of said device from said input data and determining corresponding residual data from said output data and simulated output data comprises:
Inputting the input characteristic data into a simulator to obtain simulation output data corresponding to the equipment, wherein the simulator is trained according to historical production data;
and determining a corresponding residual sequence according to the output characteristic data and the simulation output data.
5. The method as recited in claim 4, further comprising:
performing fault analysis on the residual sequence to determine a corresponding fault detection value;
if the fault detection value exceeds a fault threshold, the equipment has a fault;
if the fault detection value does not exceed the fault threshold, the equipment has no fault.
6. The method of claim 5, wherein performing fault analysis on the residual sequence to determine a corresponding fault detection value comprises:
determining a fault detection function of a corresponding type according to the type of the residual sequence, wherein the type comprises: univariate classes and/or multivariate classes;
and determining a fault detection value corresponding to the residual sequence according to the fault detection function of the corresponding type, wherein the fault threshold is related to the false alarm rate.
7. An apparatus for analyzing a device failure, said apparatus comprising:
The acquisition module is used for acquiring production data corresponding to monitoring points through sensors of the monitoring points on the equipment, wherein the production data comprises: the monitoring points comprise environment monitoring points, control monitoring points and output monitoring points, and the input data comprises at least one of the following: temperature data, humidity data, air supply quantity data, water quantity data and material data;
the residual error determining module is used for determining simulation output data of the equipment according to the input data and determining corresponding residual error data according to the output data and the simulation output data;
the fault analysis module is used for carrying out factor contribution analysis according to the input data after determining that the equipment has faults according to the residual data, and determining corresponding fault parameters;
the fault analysis module comprises:
the factor determination submodule is used for carrying out fusion processing on a plurality of input data according to a set rule to obtain a plurality of fault influence factors;
the contribution rate analysis sub-module is used for calculating fault detection statistics through a preset fault analyzer and a fault influence factor; calculating contribution rates of the plurality of fault influence factors to the fault detection statistics respectively; determining a fault influence factor with the largest contribution rate;
And the parameter determination submodule is used for determining at least one input data corresponding to the fault influence factor with the largest contribution rate as a corresponding fault parameter.
8. The apparatus of claim 7, wherein the device comprises a plurality of sensors,
and the acquisition module is used for acquiring production data of corresponding monitoring points through sensors of the monitoring points on the equipment.
9. The apparatus of claim 7, wherein said apparatus further comprises:
the data processing module is used for sorting the production data according to the time sequence; and processing the sorted production data according to the set window to respectively obtain corresponding input characteristic data and output characteristic data.
10. The apparatus of claim 9, wherein the residual determination module comprises:
the simulation processing sub-module is used for inputting the input characteristic data into a simulator to obtain simulation output data corresponding to the equipment, wherein the simulator is trained according to historical production data;
and the residual sequence determining submodule is used for determining a corresponding residual sequence according to the output characteristic data and the simulation output data.
11. The apparatus as recited in claim 10, further comprising:
The fault detection module is used for carrying out fault analysis on the residual sequence and determining a corresponding fault detection value; if the fault detection value exceeds a fault threshold, the equipment has a fault; if the fault detection value does not exceed the fault threshold, the equipment has no fault.
12. The apparatus of claim 11, wherein the fault detection module comprises:
a function determining submodule, configured to determine a fault detection function of a corresponding type according to a type of the residual sequence, where the type includes: univariate classes and/or multivariate classes;
and the detection value determining submodule is used for determining a fault detection value corresponding to the residual sequence according to the fault detection function of the corresponding type, and the fault threshold is related to the false alarm rate.
13. An electronic device, comprising: a processor; and
memory having executable code stored thereon that, when executed, causes the processor to perform the device failure analysis method of one or more of claims 1-6.
14. One or more machine readable media having executable code stored thereon that, when executed, causes a processor to perform the device fault analysis method of one or more of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811629343.9A CN111400850B (en) | 2018-12-28 | 2018-12-28 | Equipment fault analysis method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811629343.9A CN111400850B (en) | 2018-12-28 | 2018-12-28 | Equipment fault analysis method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111400850A CN111400850A (en) | 2020-07-10 |
| CN111400850B true CN111400850B (en) | 2024-04-09 |
Family
ID=71430114
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811629343.9A Active CN111400850B (en) | 2018-12-28 | 2018-12-28 | Equipment fault analysis method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111400850B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112102111B (en) * | 2020-09-27 | 2021-06-08 | 华电福新广州能源有限公司 | Intelligent processing system for power plant data |
| CN113822344B (en) * | 2021-08-30 | 2024-05-31 | 龙源(北京)新能源工程技术有限公司 | Method for monitoring state of front bearing of generator of wind turbine generator based on data driving |
| CN113984114B (en) * | 2021-10-18 | 2022-12-06 | 大连理工大学 | Method for diagnosing abnormality of underwater structure of ocean floating platform |
| CN117057676B (en) * | 2023-10-11 | 2024-02-23 | 深圳润世华软件和信息技术服务有限公司 | Multi-data fusion fault analysis method, equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103761372A (en) * | 2014-01-06 | 2014-04-30 | 上海海事大学 | Multilevel inverter fault diagnosis strategy based on principal component analysis and multi-classification related vector machine(PCA-mRVM) |
| CN105318905A (en) * | 2014-12-30 | 2016-02-10 | 国家电网公司 | Fault diagnosis method of sensor of thermal power plant thermodynamic system |
| CN105512812A (en) * | 2015-12-02 | 2016-04-20 | 中广核工程有限公司 | Nuclear power plant equipment fault early warning analysis method and system based on dynamic simulation model |
| CN106897542A (en) * | 2017-04-18 | 2017-06-27 | 浙江中烟工业有限责任公司 | Based on the cigarette cut tobacco segment fault diagnostic method that notable failure variable is extracted |
| CN107301884A (en) * | 2017-07-24 | 2017-10-27 | 哈尔滨工程大学 | A kind of hybrid nuclear power station method for diagnosing faults |
| CN107608335A (en) * | 2017-09-14 | 2018-01-19 | 山东科技大学 | A kind of UAV Flight Control System fault detect and the data-driven method of fault reconstruction |
| CN108875108A (en) * | 2017-05-16 | 2018-11-23 | 长春工业大学 | A kind of rail vehicle circuit failure diagnosis method based on PCA and BRB |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11940318B2 (en) * | 2016-09-27 | 2024-03-26 | Baker Hughes Energy Technology UK Limited | Method for detection and isolation of faulty sensors |
| CN108897977B (en) * | 2018-08-24 | 2022-10-14 | 河海大学 | Runoff evolution uncertain attribution method based on large-area hydrological simulation |
-
2018
- 2018-12-28 CN CN201811629343.9A patent/CN111400850B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103761372A (en) * | 2014-01-06 | 2014-04-30 | 上海海事大学 | Multilevel inverter fault diagnosis strategy based on principal component analysis and multi-classification related vector machine(PCA-mRVM) |
| CN105318905A (en) * | 2014-12-30 | 2016-02-10 | 国家电网公司 | Fault diagnosis method of sensor of thermal power plant thermodynamic system |
| CN105512812A (en) * | 2015-12-02 | 2016-04-20 | 中广核工程有限公司 | Nuclear power plant equipment fault early warning analysis method and system based on dynamic simulation model |
| CN106897542A (en) * | 2017-04-18 | 2017-06-27 | 浙江中烟工业有限责任公司 | Based on the cigarette cut tobacco segment fault diagnostic method that notable failure variable is extracted |
| CN108875108A (en) * | 2017-05-16 | 2018-11-23 | 长春工业大学 | A kind of rail vehicle circuit failure diagnosis method based on PCA and BRB |
| CN107301884A (en) * | 2017-07-24 | 2017-10-27 | 哈尔滨工程大学 | A kind of hybrid nuclear power station method for diagnosing faults |
| CN107608335A (en) * | 2017-09-14 | 2018-01-19 | 山东科技大学 | A kind of UAV Flight Control System fault detect and the data-driven method of fault reconstruction |
Non-Patent Citations (1)
| Title |
|---|
| 闫纪红.《可靠性与智能维护》.2011,第224页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111400850A (en) | 2020-07-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111400850B (en) | Equipment fault analysis method, device, equipment and storage medium | |
| US11243524B2 (en) | System and method for unsupervised root cause analysis of machine failures | |
| US10521490B2 (en) | Equipment maintenance management system and equipment maintenance management method | |
| US20210019211A1 (en) | Method and device for determining a performance indicator value for predicting anomalies in a computing infrastructure from values of performance indicators | |
| US20190101908A1 (en) | Plant abnormality detection method and system | |
| CN111459700A (en) | Method and apparatus for diagnosing device failure, diagnostic device, and storage medium | |
| JP2017004509A (en) | Advanced analytical infrastructure for machine learning | |
| US11755548B2 (en) | Automatic dataset preprocessing | |
| US11657121B2 (en) | Abnormality detection device, abnormality detection method and computer readable medium | |
| KR102408426B1 (en) | Method for detecting anomaly using equipment age index and apparatus thereof | |
| CN112487356A (en) | Structural health monitoring data enhancement method | |
| CN113196311A (en) | System and method for identifying and predicting abnormal sensing behavior patterns of a machine | |
| CN111382494A (en) | System and method for detecting anomalies in sensory data of industrial machines | |
| CN111061581B (en) | Fault detection method, device and equipment | |
| US20210333768A1 (en) | Control support apparatus, control support method, computer readable medium with control support program recorded thereon and control system | |
| CN104317778A (en) | Massive monitoring data based substation equipment fault diagnosis method | |
| CN115952081A (en) | Software testing method, device, storage medium and equipment | |
| Bond et al. | A hybrid learning approach to prognostics and health management applied to military ground vehicles using time-series and maintenance event data | |
| Li et al. | Meteorological radar fault diagnosis based on deep learning | |
| CN111930728A (en) | Method and system for predicting characteristic parameters and fault rate of equipment | |
| Pilario et al. | Process incipient fault detection using canonical variate analysis | |
| CN115659271A (en) | Sensor abnormality detection method, model training method, system, device, and medium | |
| KR102212022B1 (en) | Method of automatically determining condition of hydro turbine in hydroelectric power plant and system for the same | |
| RU2699685C1 (en) | Method of analyzing and monitoring the state of a technical installation comprising a plurality of dynamic systems | |
| CN117705178A (en) | Wind power bolt information detection method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |